Search

Accurate defect detection is crucial for ensuring the trustworthiness of intelligent railway systems. Current approaches either rely on static ensembling of Convolutional Neural Networks (CNNs) or on single deep-learning CNN models. Traditional methods use a large volume of data to identify underlying patterns. However, training a new defect classifier with limited samples often results in overfitting and poor performance on unseen images. To overcome these challenges, we introduce a dynamic weight adaptation mechanism within an ensemble learning framework, enhanced by state-of-the-art transfer learning models (VGG-19, MobileNetV3, and ResNet50). We obtained a good test and validation accuracy of 99%, accompanied by a precision of 0.99, and recall and F1-score of 0.98. Unlike previous methods, our approach demonstrates consistency. Particularly, techniques that involve selecting predictions based on minimum loss previously required a significant number of epochs to stabilize. Data fusion techniques are even more demanding, requiring a substantially higher number of epochs for stabilization. Conversely, our proposed method achieves stable performance and rapid convergence within just 10 epochs, and it shows minimal fluctuation in the training curve (0–5 epochs). This visibly contrasts with earlier methods, which, despite reaching similar levels of accuracy, required significantly more epochs and exhibited greater fluctuations in their training curves. Through these findings, we anticipate that the proposed dynamic weight adaptation-based ensemble approach will further research and development of reusable AI-enabled solutions for rail defect classification. [ABSTRACT FROM AUTHOR]

In the context of Industry 4.0, integrating Digital Twin (DT) technology stands out as a critical challenge for enhancing manufacturing processes and productivity. The combination of DT and Artificial Intelligence (AI) provides a significant benefit for improving processes in real-time. Industries are actively researching these technologies to keep pace with the rapid evolution of technology, utilizing virtual representations for efficient real-time monitoring and control. The present paper proposes a new approach that relies on DT technology for monitoring, optimizing manufacturing processes and enabling quality control through Deep learning (DL). The proposed methodology involves creating a digital replica of the physical system and utilizing DL models for quality control purposes. This approach improves automation and productivity while maintaining high levels of quality assurance in factories. DL is deployed within the DT for gathering data from the physical system and making predictions regarding product quality. The approach is illustrated by considering an experimental industrial prototype. The results obtained are particularly intriguing, demonstrating heightened predictive accuracy in assessing product quality and real-time issue resolution. Overall, the findings underscore the significant and interesting impact of DT technology with DL on manufacturing processes in the context of Industry 4.0. [ABSTRACT FROM AUTHOR]

This review focuses on the definitions, modalities, applications, and performance of various aspects of digital twins (DTs) in the context of transmission and industrial machinery. In this regard, the context around Industry 4.0 and even aspirations for Industry 5.0 are discussed. The many definitions and interpretations of DTs in this domain are first summarized. Subsequently, their adoption and performance levels for rotating and industrial machineries for manufacturing and lifetime performance are observed, along with the type of validations that are available. A significant focus on integrating fundamental operations of the system and scenarios over the lifetime, with sensors and advanced machine or deep learning, along with other statistical or data-driven methods are highlighted. This review summarizes how individual aspects around DTs are extremely helpful for lifetime design, manufacturing, or decision making even when a DT can remain incomplete or limited. [ABSTRACT FROM AUTHOR]

In recent years, the detection performance of SAR-GMTI (synthetic aperture radar-ground moving target indication) algorithm based on deep learning has always been limited by insufficient measured data due to the heavy operation complexity and high cost of real SAR systems. To solve this problem, this paper proposes an overall DT-based implementation framework for SAR ground moving target intelligent detection tasks. In particular, by virtue of a SAR imaging algorithm, a high-fidelity twin replica of SAR moving targets is established in digital space through parameter traversal based on the prior target characteristics of the obtained measured datasets. Then, the constructed SAR twin datasets is fed into the neural network model to train an intelligent detector by fully learning features of the moving targets and preset the SAR scene in the twin space, which can realize the robust detection of ground moving targets in related practical scenarios with no need for multiple and complex field experiments. Moreover, the effectiveness of the proposed framework is verified on the MiniSAR measured system, and a comparison with traditional CFAR detection method is given simultaneously. [ABSTRACT FROM AUTHOR]

The rapid development of advanced technologies provides futuristic option to enhance product value with digital services, which the concept of Smart Product-Service System (SPSS) was proposed. SPSS focuses on usage data, the whole lifecycle, and the iterative optimisation. A large amount of data and context information can be collected during the usage stage, which can be used to elicit requirements to guide further design. How to realise the requirement elicitation with cognitive intelligence based on usage data is the key step for design optimisation. Therefore, this research proposes a cognitive intelligence-enabled requirements elicitation framework to help designers promote the design optimisation process. First, the digital twin-driven data collection architecture of SPSS is proposed by considering multi-sources and multi-stages. Second, the behaviour of SPSS is modelled based on Auto-Encoder which is constructed using deep learning to cognise SPSS performance. Third, the corresponding behaviour model is interpreted based on Shapley Addictive exPlanations (SHAP) to discover key factors with cognitive intelligence. Finally, the domain knowledge graph is used to generate the optimisation requirements for further design. To demonstrate the feasibility and advantages of the proposed framework, this study adopts the case study of wind turbines for illustration and verification. [ABSTRACT FROM AUTHOR]

Gear fault detection and remaining useful life estimation are important tasks for monitoring the health of rotating machinery. In this study, a new benchmark for endurance gear vibration signals is presented and made publicly available. The new dataset was used in the HUMS 2023 conference data challenge to test anomaly detection algorithms. A survey of the suggested techniques is provided, demonstrating that traditional signal processing techniques interestingly outperform deep learning algorithms in this case. Of the 11 participating groups, only those that used traditional approaches achieved good results on most of the channels. Additionally, we introduce a signal processing anomaly detection algorithm and meticulously compare it to a standard deep learning anomaly detection algorithm using data from the HUMS 2023 challenge and simulated signals. The signal processing algorithm surpasses the deep learning algorithm on all tested channels and also on simulated data where there is an abundance of training data. Finally, we present a new digital twin that enables the estimation of the remaining useful life of the tested gear from the HUMS 2023 challenge. [ABSTRACT FROM AUTHOR]

Urban water management faces new challenges due to the rise of digital solutions and abundant data, leading to the development of data-centric tools for decision-making in global water utilities, with AI technologies poised to become a key trend in the sector. This paper proposes a novel methodology for optimal sensor placement aimed at supporting the creation of a digital twin for water infrastructure. A significant innovation in this study is the creation of a metamodel to estimate pressure at consumption nodes in a water supply system. This metamodel guides the optimal sensor configuration by minimizing the difference between estimated and observed pressures. Our methodology was tested on a synthetic case study, showing accurate results. The estimated pressures at each network node exhibited low error and high accuracy across all sensor configurations tested, highlighting the potential for future development of a digital twin for water distribution systems. [ABSTRACT FROM AUTHOR]

The safe and steady operation of hydropower generation systems is crucial for electricity output in the grid. However, hydropower stations have complicated interior structures, making defect detection difficult without disassembly inspections. The application of digital modeling to hydropower stations will effectively promote the intelligent transformation of hydropower stations as well as reduce the maintenance costs of the system. This study provides a model of the power generating and transmission system for hydropower plants, with an emphasis on primary equipment and measured data. The model utilizes PSCAD to digitalize state response in hydropower plants with various short-circuit faults. The fault information is identified and learned using the Adaptive Time–Frequency Memory (AD-TFM) deep learning model. It is demonstrated that our proposed method can effectively obtain the fault information through radio frequency identification (RFID). The accuracy of the traditional method is 0.90, while the results for AD-TFM show a fault classification accuracy of 0.92, which is more than enough to identify multiple fault types compared to the existing methods. [ABSTRACT FROM AUTHOR]

The accidental leakage of gaseous hydrogen from hydrogen refueling station facilities has the potential to result in a large fire and explosion catastrophe. The ability to forecast the spatiotemporal evolution of hydrogen plumes in real-time is crucial for monitoring the distribution of plume concentrations and mitigating the risk of fire and explosion. The utilization of deep learning has been extensively employed in a diverse range of spatiotemporal forecasting tasks. However, these approaches encounter limitations in accurately quantifying uncertainty when predicting spatiotemporal concentrations and plume boundaries. This research paper introduces a novel model called DPSTNN_H 2 Evolution, which is a deep probabilistic spatial-temporal neural network designed for forecasting the spatiotemporal evolution of hydrogen plumes. The benchmark dataset is constructed by the implementation of numerical simulations pertaining to the inadvertent leak of hydrogen within a hydrogen refueling station. The findings of the study indicate that incorporating quantified uncertainty information might enhance the precision of plume boundaries and the resilience of plume concentrations when predicting the spatiotemporal development of hydrogen. By employing Monte Carlo sampling with a sample size of m = 100 and a dropout rate of p = 0.1 , the model demonstrates the ability to provide real-time inference for 10 instances of plumes, while maintaining a high level of accuracy with R2 = 0.9829. In comparison to the current state-of-the-art model, the proposed model demonstrates superior accuracy and robustness in forecasting the spatiotemporal evolution of hydrogen plumes. In general, our proposed model has the potential to serve as a dependable option for the development of a digital twin for emergency management of hydrogen refueling stations. • Probabilistic spatial-temporal neural network model for hydrogen plume evolutions is proposed. • Normalized uncertainty contours and uncertainty intervals to improve accuracy and robustness. • Numerical experiment of hydrogen leakage and dispersion in refueling station are conducted. • Optimal hyper-parameters of the proposed model are determined • Comparison between the proposed model with point-estimation based model is conducted [ABSTRACT FROM AUTHOR]

Modern cyber–physical production systems provide advanced solutions to enhance factory throughput and efficiency. However, monitoring its behaviour and performance becomes challenging as the complexity of a manufacturing system increases. Artificial Intelligence (AI) provides techniques to manage not only decision-making tasks but also to support monitoring. The integration of AI into a factory can be facilitated by a reliable Digital Twin (DT) that enables knowledge-based and data-driven approaches. While computer vision and convolutional neural networks (CNNs) are crucial for monitoring production systems, the need for extensive training data hinders their adoption in real factories. The proposed methodology leverages the Digital Twin of a factory to generate labelled synthetic data for training CNN-based object detection models. Regarding their position and state, the focus is on monitoring entities in manufacturing systems, such as parts, components, fixtures, and tools. This approach reduces the need for large training datasets and enables training when the actual system is unavailable. The trained CNN model is evaluated in various scenarios, with a real case study involving an industrial pilot plant for repairing and recycling Printed Circuit Boards (PCBs). [ABSTRACT FROM AUTHOR]

Effective monitoring of road fixtures is essential for urban safety and functionality. However, traditional inspections are time-consuming, costly, and error prone, while current automated solutions struggle with high initial setup costs, limited flexibility preventing wide adaptation, and reliance on centralized processing that can delay response times. This study introduces an edge AI-based remote road fixture monitoring system which automatically and continuously updates the information of the road digital twin (DT). The main component is a small-sized edge device consisting of a camera, GPS, and IMU sensors designed to be installed in typical cars. The device captures images, detects the fixture, and estimates their location by employing deep learning and feature matching. This information is transmitted to a dedicated cloud server and represented on a user-friendly user interface. Experiments were conducted to test the system's performance. The results showed that the device could successfully detect the fixture and estimate their global coordinates. Outputs were marked and shown on the road DT, proving the integrated and smooth operation of the whole system. The proposed Edge AI device demonstrated that it could significantly reduce the data size by 80–84% compared to traditional methods. With a satisfactory object detection accuracy of 65%, the system effectively identifies traffic poles, stop signs, and streetlights, integrating these findings into a digital twin for real-time monitoring. The proposed system improves road monitoring by cutting down on maintenance and emergency response times, increasing the ease of data use, and offering a foundation for an overview of urban road fixtures' current state. However, the system's reliance on the quality of data collected under varying environmental conditions suggests potential improvements for consistent performance across diverse scenarios. [ABSTRACT FROM AUTHOR]

To facilitate the integration of autonomous unmanned air vehicles (UAVs) in day-to-day life, it is imperative that safe navigation can be demonstrated in all relevant scenarios. For UAVs using a navigational protocol driven by artificial neural networks, training and testing data from multiple environmental contexts are needed to ensure that bias is minimised. The reduction in predictive capacity when faced with unfamiliar data is a common weak point in trained networks, which worsens the further the input data deviates from the training data. However, training for multiple environmental variables dramatically increases the man-hours required for data collection and validation. In this work, a potential solution to this data availability issue is presented through the generation and evaluation of photo-realistic image datasets from a simulation of 3D-scanned physical spaces which are theoretically linked in a digital twin (DT) configuration. This simulation is then used to generate environmentally varied iterations of the target object in that physical space by two contextual variables (weather and daylight). This results in an expanded dataset of bicycles that contains weather and time-varied components of the same images which are then evaluated using a generic build of the YoloV3 object detection network; the response is then compared to two real image (night and day) datasets as a baseline. The results reveal that the network response remained consistent across the temporal axis, maintaining a measured domain shift of approximately 23% between the two baselines. [ABSTRACT FROM AUTHOR]

The rapier loom works in a complex environment and operates at high speeds. It is inevitable that its performance will deteriorate during the production process, which in turn will cause faults. The development of maintenance has undergone the transition from "regular maintenance" and "post-event maintenance" to "predictive maintenance". In order to achieve the synergistic optimization goal of ensuring operational safety and reducing operational costs, a predictive maintenance method driven by the fusion of digital twin and deep learning is proposed based on the idea of "combining the real with the virtual and controlling the real". Firstly, a digital twin system structure model of rapier weaving machine is constructed, and the overall architecture of digital twin is proposed according to the full operation cycle of rapier weaving machine. Then, the digital twin-driven process parameter evaluation and prediction and health state evaluation and prediction are investigated separately. In order to achieve the evaluation and prediction of process parameters to ensure the efficiency of weaving machine operation, the prediction method of IWOA optimized BP neural network driven by twin data is proposed and the model is updated and optimized based on the martingale distance approach. In order to achieve health state assessment and prediction, we use health index as an evaluation index to characterize the health condition of spindles, and use BiLSTM network to achieve prediction of remaining spindle life and then make maintenance decisions. The results show that there are greater advantages to combining deep learning and digital twin technology for intelligent predictive maintenance of rapier loom. [ABSTRACT FROM AUTHOR]

Due to the strong nonlinear interaction between the flow field and blades, the prediction of turbine energy acquisition capacity is still quite complex, the traditional methods take too long time to evaluate. In this article, the digital twin model + CFD simulation + monitor data are used for turbine energy efficiency assessment. A self-designed vertical wave flow turbine (VWFT) is taken as the research object, the prediction takes into account the coupling of the VWFT for motion and blade rotation, which is in good agreement with the monitor data at sea. The simulations show that the torque, thrust force and lateral force flow rate data can be loaded from the database into the digital model. If those data are not in the database, the interpolation method is used along with deep learning of recurrent neural network to obtain the energy harvesting parameters, all the error is no more than 10%. [ABSTRACT FROM AUTHOR]

The integration of artificial intelligence (AI) with Digital Twins (DTs) has emerged as a promising approach to revolutionize healthcare, particularly in terms of diagnosis and management of thoracic disorders. This study proposes a comprehensive framework, named Lung-DT, which leverages IoT sensors and AI algorithms to establish the digital representation of a patient's respiratory health. Using the YOLOv8 neural network, the Lung-DT system accurately classifies chest X-rays into five distinct categories of lung diseases, including "normal", "covid", "lung_opacity", "pneumonia", and "tuberculosis". The performance of the system was evaluated employing a chest X-ray dataset available in the literature, demonstrating average accuracy of 96.8%, precision of 92%, recall of 97%, and F1-score of 94%. The proposed Lung-DT framework offers several advantages over conventional diagnostic methods. Firstly, it enables real-time monitoring of lung health through continuous data acquisition from IoT sensors, facilitating early diagnosis and intervention. Secondly, the AI-powered classification module provides automated and objective assessments of chest X-rays, reducing dependence on subjective human interpretation. Thirdly, the twin digital representation of the patient's respiratory health allows for comprehensive analysis and correlation of multiple data streams, providing valuable insights as to personalized treatment plans. The integration of IoT sensors, AI algorithms, and DT technology within the Lung-DT system demonstrates a significant step towards improving thoracic healthcare. By enabling continuous monitoring, automated diagnosis, and comprehensive data analysis, the Lung-DT framework has enormous potential to enhance patient outcomes, reduce healthcare costs, and optimize resource allocation. [ABSTRACT FROM AUTHOR]

With the development of collaborative edge computing (CEC), the manufacturing market is gradually moving toward large-scale, multi-scenario, and dynamic directions. The existing scheduling strategies based on machine learning or deep learning are only applicable to specific scenarios, which is difficult to meet the requirements of dynamic real-time scheduling in multiple scenarios. The proposed digital twin technology provides a new solution for real-time scheduling of multiple scenarios. In this paper, a digital twin-oriented multi-scene real-time scheduler (GNN-RL) is proposed. This scheduler converts task sequences into node trees and sets up two learning layers. The first layer is an online learning representation layer, which uses GNN to learn node features of embedded structures in real time to boost large instances without additional training. The second layer is the online learning policy layer, which introduces imitation learning mappings into optimal scheduling behavior policies adapted to multiple scenarios. Finally, our approach is validated in several scenarios in 3D digital twin factories, such as computationally intensive, delay-sensitive, and task-urgent scenarios. Since the scheduler proposed in this paper learns general features of the embedding graph rather than instance-specific features, it has good generality and scalability, with good generalization and scalability, outperforming other scheduling rules and schedulers on various benchmarks. [ABSTRACT FROM AUTHOR]

Due to the harsh environment of highway tunnels and frequent breakdowns of various detection sensors and surveillance devices, the operational management of highway tunnels lacks effective data support. This paper analyzes the characteristics of operational surveillance data in highway tunnels. It proposes a multimodal information fusion method based on CNN-LSTM-attention and designs and develops a digital twin for highway tunnel operations. The system addresses issues such as insufficient development and coordination of the technical architecture of operation control systems, weak information service capabilities, and insufficient data application capabilities. The system also lacks intelligent decision-making and control capabilities. The developed system achieves closed-loop management of "accurate perception-risk assessment-decision warning-emergency management" for highway tunnel operations based on data-driven approaches. The engineering demonstration application underscores the system's capacity to enhance tunnel traffic safety, diminish tunnel management costs, and elevate tunnel driving comfort. [ABSTRACT FROM AUTHOR]

For a lithium-ion (Li-ion) battery to operate safely and reliably, an accurate state of health (SOH) estimation is crucial. Data-driven models with manual feature extraction are commonly used for battery SOH estimation, requiring extensive expert knowledge to extract features. In this regard, a novel data pre-processing model is proposed in this paper to extract health-related features automatically from battery-discharging data for SOH estimation. In the proposed method, one-dimensional (1D) voltage data are converted to two-dimensional (2D) data, and a new data set is created using a 2D sliding window. Then, features are automatically extracted in the machine learning (ML) training process. Finally, the estimation of the SOH is achieved by forecasting the battery voltage in the subsequent cycle. The performance of the proposed technique is evaluated on the NASA public data set for a Li-ion battery degradation analysis in four different scenarios. The simulation results show a considerable reduction in the RMSE of battery SOH estimation. The proposed method eliminates the need for the manual extraction and evaluation of features, which is an important step toward automating the SOH estimation process and developing battery digital twins. [ABSTRACT FROM AUTHOR]

Hydrogen release and dispersion from hydrogen refuelling stations have the potential to cause explosion disaster and bring significant causalities and economic losses to the surroundings. Real-time spatial hydrogen plume concentration prediction is essential for the quick emergency response planning to dissipate such flammable vapor cloud and prevent explosion disaster. Deep learning approaches have recently been applied to real-time gas release and dispersion modeling, however, are 'over-confident' for spatial plume concentration and boundary estimation, which could not support the robust decision-makings. This study proposes a hybrid deep probability learning-based spatial hydrogen plume concentration prediction model, namely DPL_H 2 Plume by integrating deep learning and Variational Bayesian Inference. Numerical model of hydrogen release and dispersion from hydrogen refuelling station is built to construct the benchmark dataset. By using such dataset, two pre-defined parameters, namely Monte Carlo sampling number m = 300 and dropout probability p = 0.1 are determined to ensure the model's tradeoff between inference accuracy and efficiency. Comparison between our proposed model and the state-of-the-art model is also conducted. The results demonstrate that our model exhibits a competitive accuracy of R 2 = 0.97 as well as an inference time 3.32 s. In addition, our model gives the comprehensive estimations including not only spatial hydrogen plume concentration but also its uncertainty. Also, our model provides the more accurate estimation at plume boundary compared to the state-of-the-art model. Overall, our proposed model could provide reliable alternative for constructing a digital twin for emergency management of hydrogen refuelling station. • Deep probabilistic learning-based hydrogen plume prediction model is proposed. • Optimal hyperparameters of variational Bayesian inference are determined. • Model accurately predicts real-time spatial hydrogen plume concentration given scenario-related parameters. • Model predicts additional uncertainty information for comprehensive emergency decision-makings. [ABSTRACT FROM AUTHOR]

Industrial collaborative robots play an essential role in smart manufacturing because they improve productivity while also ensuring workplace safety. However, the development of prognostic and health management systems to ensure the reliability of these robots has been a major challenge due to the lack of fault data. This paper proposed a digital twin scheme based on the fusion of the robot kinematic and dynamic models' information down to the powertrains (i.e., the joints motor, and gear) along with the control algorithms and uncertainty accommodation based upon deep learning. The presented digital twin concept has the potential to propel simulation-based fault prediction. We also highlight and discuss challenges and opportunities around the development of the hybrid digital twin for condition monitoring of industrial collaborative robots. [ABSTRACT FROM AUTHOR]

The rapid rise of artificial intelligence (AI) in medicine in the last few years highlights the importance of developing bigger and better systems for data and model sharing. However, the presence of Protected Health Information (PHI) in medical data poses a challenge when it comes to sharing. One potential solution to mitigate the risk of PHI breaches is to exclusively share pre-trained models developed using private datasets. Despite the availability of these pre-trained networks, there remains a need for an adaptable environment to test and fine-tune specific models tailored for clinical tasks. This environment should be open for peer testing, feedback, and continuous model refinement, allowing dynamic model updates that are especially important in the medical field, where diseases and scanning techniques evolve rapidly. In this context, the Discovery Viewer (DV) platform was developed in-house at the Biomedical Engineering and Imaging Institute at Mount Sinai (BMEII) to facilitate the creation and distribution of cutting-edge medical AI models that remain accessible after their development. The all-in-one platform offers a unique environment for non-AI experts to learn, develop, and share their own deep learning (DL) concepts. This paper presents various use cases of the platform, with its primary goal being to demonstrate how DV holds the potential to empower individuals without expertise in AI to create high-performing DL models. We tasked three non-AI experts to develop different musculoskeletal AI projects that encompassed segmentation, regression, and classification tasks. In each project, 80% of the samples were provided with a subset of these samples annotated to aid the volunteers in understanding the expected annotation task. Subsequently, they were responsible for annotating the remaining samples and training their models through the platform's "Training Module". The resulting models were then tested on the separate 20% hold-off dataset to assess their performance. The classification model achieved an accuracy of 0.94, a sensitivity of 0.92, and a specificity of 1. The regression model yielded a mean absolute error of 14.27 pixels. And the segmentation model attained a Dice Score of 0.93, with a sensitivity of 0.9 and a specificity of 0.99. This initiative seeks to broaden the community of medical AI model developers and democratize the access of this technology to all stakeholders. The ultimate goal is to facilitate the transition of medical AI models from research to clinical settings. [ABSTRACT FROM AUTHOR]

As the complexity and scale of modern networks continue to grow, the need for efficient, secure management, and optimization becomes increasingly vital. Digital twin (DT) technology has emerged as a promising approach to address these challenges by providing a virtual representation of the physical network, enabling analysis, diagnosis, emulation, and control. The emergence of Software-defined network (SDN) has facilitated a holistic view of the network topology, enabling the use of Graph neural network (GNN) as a data-driven technique to solve diverse problems in future networks. This survey explores the intersection of GNNs and Network digital twins (NDTs), providing an overview of their applications, enabling technologies, challenges, and opportunities. We discuss how GNNs and NDTs can be leveraged to improve network performance, optimize routing, enable network slicing, and enhance security in future networks. Additionally, we highlight certain advantages of incorporating GNNs into NDTs and present two case studies. Finally, we address the key challenges and promising directions in the field, aiming to inspire further advancements and foster innovation in GNN-based NDTs for future networks. [ABSTRACT FROM AUTHOR]

The article discusses the modeling of the use of digital twin technologies (a digital twin) for the task of organizing long-term storage of various types of documents. A digital twin in this respect differs from a digital copy, which has no connection with the real original object. A review of the problem was carried out. We argue that, despite the active use of digital twin technology in various areas, its applications in the area of long-term storage of documents remain limited. At the same time, the task of increasing the durability of documents during long-term storage remains important and largely unresolved. The complexity of solving the problem of long-term storage of documents is considered, and a formal statement of the problem of long-term storage using digital twin technologies is carried out. Destructive factors that affect long-term storage documents and significantly reduce their durability have been identified. A system of indicators has been developed to assess the durability (preservation) of documents. The modeling of the use of digital twin technology in the organization of long-term preservation within the framework of Industry 4.0 was carried out. In the course of modeling, the goals and the strategies of long-term storage were established. Primary mathematical models for controlling destructive factors as well as technological solutions for digital twin long-term storage are proposed. It is assumed that the key part of this technology is the Industrial Internet of Things. The effectiveness of the use of digital twin technologies for solving the problem was assessed. The spheres of application and further ways of research are determined. [ABSTRACT FROM AUTHOR]

With the remarkable technological development in cyber-physical systems, industry 4.0 has evolved by use of a significant concept named digital twin (DT). However, it is still difficult to construct a relationship between twin simulation and a real scenario considering dynamic variations, especially when dealing with small surface defect detection tasks with high performance and computation resource requirements. In this article, we aim to construct cyber-manufacturing systems to achieve a DT solution for small surface defect detection task. Focusing on DT-based solution, the proposed system consists of an Edge-Cloud architecture and a surface defect detection algorithm. Considering dynamic characteristics and real-time response requirement, Edge-Cloud architecture is built to achieve smart manufacturing by efficiently collecting, processing, analyzing, and storing data produced by factory. A deep learning-based algorithm is then constructed to detect surface defeats based on multi-modal data, i.e., imaging and depth data. Experiments show the proposed algorithm could achieve high accuracy and recall in small defeat detection task, thus constructing DT in cyber-manufacturing. [ABSTRACT FROM AUTHOR]

Groundwater resource analysis is an important technological means of avoiding disease and controlling water pollution. In this field of study, water quality assessments are conducted using sequential parametric values collected in real time. For evaluation reasons, several state-of-the-art water quality evolution mechanism typically employs a single time-invariant model to determine the quality of Water. As a result, it is challenging to illustrate the importance of randomness and contingency in the process of water quality assessment, leading to variations and errors in the procedure of quality assessment. In consideration of these limitations, this study proposes a Digital Twin inspired Hybrid System (DTHS) for water quality assessment in real time. In addition, the degree of water quality is offered as an indication for quantitatively assessing the health risk status. Observational data from a monitoring station in Chaheru, a locality in the Phagwara district of the Indian state of Punjab, are used to demonstrate the efficacy of the proposed approach. The experimental results demonstrate the effectiveness of the proposed framework in terms of water quality determination, computational cost, and stability. The framework has achieved higher prediction accuracy (94.14%), sensitivity (93.74%), specificity (91.47%), and f-measure (92.37%), indicating its ability to accurately determine water quality. Additionally, the framework offers reduced computational delay and improved reliability and stability, making it a trustworthy solution for timely predictions with respect to water quality. [ABSTRACT FROM AUTHOR]

Network Function Virtualization (NFV) allows for the dynamic provisioning of Virtual Network Functions (VNFs), adapting services to the complex and dynamic network environment to enhance network performance. However, VNF migration and energy consumption pose significant challenges due to the dynamic nature of the physical network. In order to maximize the acceptance rate of Service Function Chain Requests (SFCR), and reduce VNF migration and energy consumption as much as possible, we summarize several related factors such as the node hosting state, link hosting state, energy consumption, migrated nodes, and whether the mapping is successful. We define the Markov decision process by considering the factors mentioned above. Next, we design the VNF migration algorithm utilizing actor–critic models, graph convolution networks, and LSTM networks. In order to reduce the risk of trial and error during training and prediction in deep reinforcement learning scenarios, we designed a network architecture based on a digital twin (DT). In simulation experiments, compared with the FF algorithm that greedily selects the first available node, our AC_GCN algorithm significantly improves the acceptance rate of SFC requests by 2.9 times more than the FF algorithm in small topology experiments, and 27 times more than the FF algorithm in large topology experiments. Compared with the deep reinforcement learning (DRL) algorithm, which does not consider all the above factors together, for the small topology experiment, our AC_GCN algorithm outperforms the DRL algorithm in terms of request acceptance rate by 13%, underperforms compared to the DRL algorithm in terms of energy consumption by 3.8%, and underperforms compared to the DRL algorithm in terms of the number of migrated nodes for 22%; for the large topology experiment, our AC_GCN algorithm outperforms the DRL algorithm in terms of the request acceptance rate by 7.7%, outperforms the DRL algorithm in terms of energy consumption by 0.4%, and outperforms the DRL algorithm in terms of the number of migrated nodes by 1.6%. [ABSTRACT FROM AUTHOR]

Convolutional neural networks (CNNs) have been widely used for object recognition and grasping posture planning in intelligent robotic grasping (IRG). Compared with the traditional usage of CNNs in image recognition, IRGs require high recognition accuracy and computational efficiency. However, the existing methodologies for CNN architecture design often rely on human experience and numerous trial-and-error attempts, which make it a very challenging task to obtain an optimal CNN for IRGs. To tackle this challenge, this paper develops a new differentiable architecture search (DARTS) method considering the floating-point operations (FLOPs) of CNNs, named the DARTS-F method, which converts the discrete CNN architecture search to a gradient-based continuous optimization problem and considers both the prediction accuracy and the computational cost of the CNN during the optimization. To efficiently identify the optimal neural network, this paper adopts a bilevel optimization, which first trains the neural network weights in the inner level and then optimizes the neural network architecture by fine-tuning the operational variables in the outer level. In addition, a new digital twin (DT) of IRG is developed considering the physics of realistic robotic grasping in the DT's virtual space, which could not only improve the IRG accuracy but also avoid the expensive training time. In the experiments, the proposed DARTS-F method could generate an optimized CNN with higher prediction accuracy and lower FLOPs than those obtained by the original DARTS method. The DT framework improves the accuracy of real robotic grasping from 61 to 71%. [ABSTRACT FROM AUTHOR]

Collaborative tasks in multiple systems have attracted considerable attention in contemporary manufacturing environments. Collaborative robots are representative agents for various collaborative industrial tasks. This study focuses on contactless delivery by considering multiple agents. A contactless delivery operation must be performed with well-synchronized cooperation among the sender, a receiver, and flying dynamics of the deliverable. The most challenging task is to predict the catching point of a thrown package by considering both collaborative robots. Accurate catching-point prediction and relevant operations were achieved using the proposed physics-informed neural network-based hybrid multi-stream deep learning framework. Various cooperative environments were considered using multi-modal input data and manufacturing conditions. The proposed framework incorporates these constraints, and the prediction is guided by flying dynamics and trajectory data. The effectiveness of the proposed framework was demonstrated by implementing multi-agent and related manufacturing environments in a digital twin system. The effectiveness of the proposed framework was proven experimentally using analyses and comparisons with existing machine learning methods. [ABSTRACT FROM AUTHOR]

Due to the recent rapid development of the ICT (Information and Communications Technology) field, the industrial sector is also experiencing rapid informatization. As a result, malware targeting information leakage and financial gain are increasingly found within IIoT (the Industrial Internet of Things). Moreover, the number of malware variants is rapidly increasing. Therefore, there is a pressing need for a safe and preemptive malware detection method capable of responding to these rapid changes. The existing malware detection method relies on specific byte sequence inclusion in a binary file. However, this method faces challenges in impacting the system or detecting variant malware. In this paper, we propose a data augmentation method based on an adversarial generative neural network to maintain a secure system and acquire necessary learning data. Specifically, we introduce a digital twin environment to safeguard systems and data. The proposed system creates fixed-size images from malware binaries in the virtual environment of the digital twin. Additionally, it generates new malware through an adversarial generative neural network. The image information produced in this manner is then employed for malware detection through deep learning. As a result, the detection performance, in preparation for the emergence of new malware, demonstrated high accuracy, exceeding 97%. [ABSTRACT FROM AUTHOR]

Digital twins (DTs) are becoming increasingly popular in various industries, and their potential for healthcare in the metaverse continues to attract attention. The metaverse is a virtual world where individuals interact with digital replicas of themselves and the environment. This paper focuses on personalized and precise medicine and examines the current application of DTs in healthcare within the metaverse. Healthcare practitioners may use immersive virtual worlds to replicate medical scenarios, improve teaching experiences, and provide personalized care to patients. However, the integration of DTs in the metaverse poses technical, regulatory, and ethical challenges that need to be addressed, including data privacy, standards, and accessibility. Through this examination, we aim to provide insights into the transformative potential of DTs in healthcare within the metaverse and encourage further research and development in this exciting domain. [ABSTRACT FROM AUTHOR]

In this study, we propose a population-based, data-driven intelligent controller that leverages neural-network-based digital twins for hypothesis testing. Initially, a diverse set of control laws is generated using genetic programming with the digital twin of the system, facilitating a robust response to unknown disturbances. During inference, the trained digital twin is utilized to virtually test alternative control actions for a multi-objective optimization task associated with each control action. Subsequently, the best policy is applied to the system. To evaluate the proposed model predictive control pipeline, experiments are conducted on a multi-mode heat transfer test rig. The objective is to achieve homogeneous cooling over the surface, minimizing the occurrence of hot spots and energy consumption. The measured variable vector comprises high dimensional infrared camera measurements arranged as a sequence (655,360 inputs), while the control variable includes power settings for fans responsible for convective cooling (3 outputs). Disturbances are induced by randomly altering the local heat loads. The findings reveal that by utilizing an evolutionary algorithm on measured data, a population of control laws can be effectively learned in the virtual space. This empowers the system to deliver robust performance. Significantly, the digital twin-assisted, population-based model predictive control (MPC) pipeline emerges as a superior approach compared to individual control models, especially when facing sudden and random changes in local heat loads. Leveraging the digital twin to virtually test alternative control policies leads to substantial improvements in the controller's performance, even with limited training data. [ABSTRACT FROM AUTHOR]

Digital twin is the digital representation of an entity, and it drives Industry 4.0. This paper presents a bibliometric analysis of digital twin in the supply chain to help researchers, industry practitioners, and academics to understand the trend, development, and focus of the areas of digital twin in the supply chain. This paper found several key clusters of research, including the designing of a digital twin model, integration of a digital twin model, application of digital twin in quality control, and digital twin in digitalization. In the embryonic stage of research, digital twin was tested in the production line with limited optimization. In the development stage, the importance of digital twin in Industry 4.0 was observed, as big data, machine learning, Industrial Internet of Things, blockchain, edge computing, and cloud-based systems complemented digital twin models. Digital twin was applied to improve sustainability in manufacturing and production logistics. In the current prosperity stage with high annual publications, the recent trends of this topic focus on the integration of deep learning, data models, and artificial intelligence for digitalization. This bibliometric analysis also found that the COVID-19 pandemic drove the start of the prosperity stage of digital twin research in the supply chain. Researchers in this field are slowly moving towards applying digital twin for human-centric systems and mass personalization to prepare to transit to Industry 5.0. [ABSTRACT FROM AUTHOR]

Wind and photovoltaic (PV) power forecasting are crucial for improving the operational efficiency of power systems and building smart power systems. However, the uncertainty and instability of factors affecting renewable power generation pose challenges to power system operations. To address this, this paper proposes a digital twin-based method for predicting wind and PV power. By utilizing digital twin technology, this approach provides a highly realistic simulation environment that enables accurate monitoring, optimal control, and decision support for power system operations. Furthermore, a digital twin platform for the AI (Artificial Intelligence) Grid is established, allowing real-time monitoring, and ensuring the safe, reliable, and stable operation of the grid. Additionally, a deep learning-based model WPNet is developed to predict wind and PV power at specific future time points. Four datasets are constructed based on weather conditions and historical wind and PV power data from the Flanders and Wallonia regions. The prediction models presented in this paper demonstrate excellent performance on these datasets, achieving mean square error (MSE) values of 0.001399, 0.001833, 0.000704, and 0.002708; mean absolute error (MAE) values of 0.025164, 0.027854, 0.018592, and 0.033501; and root mean square error (RMSE) values of 0.037409, 0.042808, 0.026541, and 0.052042, respectively. [ABSTRACT FROM AUTHOR]

To address the issue of the insufficient safety monitoring of power maintenance vehicles during power operations, this study proposes a vehicle monitoring scheme based on ultra wideband (UWB) and deep learning. The UWB localization algorithm employs Chaotic Particle Swarm Optimization (CSPO) to optimize the Time Difference of Arrival (TDOA)/Angle of Arrival (AOA) locating scheme in order to overcome the adverse effects of the non-visual distance and multipath effects in substations and significantly improve the positioning accuracy of vehicles. To solve the problem of the a large aspect ratio and the angle in the process of power maintenance vehicle operation situational awareness in the mechanical arm of the maintenance vehicle, the arm recognition network is based on the You Only Look Once version 5 (YOLOv5) and modified by Convolutional Block Attention Module (CBAM). The long-edge definition method with circular smoothing label, SIoU loss function, and HardSwish activation function enhance the precision and processing speed for the arm state. The experimental results show that the proposed CPSO-TDOA/AOA outperforms other algorithms in localization accuracy and effectively attenuates the non-visual distance and multipath effects. The recognition accuracy of the YOLOv5-CSL-CBAM network is substantially improved; the mAP value of the vehicles arm reaches 85.04%. The detection speed meets the real-time requirement, and the digital twin of the maintenance vehicle is effectively realized in the 3D substation model. [ABSTRACT FROM AUTHOR]

Localizing leakages in large water distribution systems is an important and ever-present problem. Due to the complexity originating from water pipeline networks, too few sensors, and noisy measurements, this is a highly challenging problem to solve. In this work, we present a methodology based on generative deep learning and Bayesian inference for leak localization with uncertainty quantification. A generative model, utilizing deep neural networks, serves as a probabilistic surrogate model that replaces the full equations, while at the same time also incorporating the uncertainty inherent in such models. By embedding this surrogate model into a Bayesian inference scheme, leaks are located by combining sensor observations with a model output approximating the true posterior distribution for possible leak locations. We show that our methodology enables producing fast, accurate, and trustworthy results. It showed a convincing performance on three problems with increasing complexity. For a simple test case, the Hanoi network, the average topological distance (ATD) between the predicted and true leak location ranged from 0.3 to 3 with a varying number of sensors and level of measurement noise. For two more complex test cases, the ATD ranged from 0.75 to 4 and from 1.5 to 10, respectively. Furthermore, accuracies upwards of 83%, 72%, and 42% were achieved for the three test cases, respectively. The computation times ranged from 0.1 to 13 s, depending on the size of the neural network employed. This work serves as an example of a digital twin for a sophisticated application of advanced mathematical and deep learning techniques in the area of leak detection. [ABSTRACT FROM AUTHOR]

Remote monitoring and maintenance are important for improving the performance of production systems. However, existing studies on this topic usually focus on the monitoring and maintenance of the working conditions of the equipment and pay relatively less attention to the processing craft and processing quality. In addition, as far as we know, there are relatively few industrial case studies on the real applications of remote monitoring and maintenance systems that include both conventional and advanced maintenance techniques under the context of Industry 4.0. Addressing these issues, an industrial case study on the monitoring and maintenance service system for a robot-driven carbon block polishing service system is presented, including its application background and engineering problems, software/hardware architecture and running logic, the monitoring and maintenance-related enabling techniques, and the configuration and operation workflows of the system in the form of screenshots of the functional WebAPPs of the software system. The case study can provide real examples and references for the industrial application of remote monitoring and maintenance service systems on industrial product service systems under the context of Industry 4.0. Advanced techniques such as the Industrial Internet of Things, digital twins, deep learning, and edge/cloud/fog computing have been applied to the system. [ABSTRACT FROM AUTHOR]

Today's healthcare facilities require new digital tools to cope with the rapidly increasing demand for technology that can support healthcare operators. The advancement of technology is leading to the pervasive use of IoT devices in daily life, capable of acquiring biomedical and biometric parameters, and providing an opportunity to activate new tools for the medical community. Digital twins (DTs) are a form of technology that are gaining more prominence in these scenarios. Many scientific research papers in the literature are combining artificial intelligence (AI) with DTs. In this work, we propose a case study including a proof of concept based on microservices, the heart DT, for the evaluation of electrocardiogram (ECG) signals by means of an artificial intelligence component. In addition, a higher-level platform is presented and described for the complete management and monitoring of cardiac pathologies. The overall goal is to provide a system that can facilitate the patient–doctor relationship, improve medical treatment times, and reduce costs. [ABSTRACT FROM AUTHOR]

This article introduces a novel framework for diagnosing faults in rolling bearings. The framework combines digital twin data, transfer learning theory, and an enhanced ConvNext deep learning network model. Its purpose is to address the challenges posed by the limited actual fault data density and inadequate result accuracy in existing research on the detection of rolling bearing faults in rotating mechanical equipment. To begin with, the operational rolling bearing is represented in the digital realm through the utilization of a digital twin model. The simulation data produced by this twin model replace traditional experimental data, effectively creating a substantial volume of well-balanced simulated datasets. Next, improvements are made to the ConvNext network by incorporating an unparameterized attention module called the Similarity Attention Module (SimAM) and an efficient channel attention feature referred to as the Efficient Channel Attention Network (ECA). These enhancements serve to augment the network's capability for extracting features. Subsequently, the enhanced network model is trained using the source domain dataset. Simultaneously, the trained model is transferred to the target domain bearing using transfer learning techniques. This transfer learning process enables the accurate fault diagnosis of the main bearing to be achieved. Finally, the proposed method's feasibility is validated, and a comparative analysis is conducted in comparison with similar approaches. The comparative study demonstrates that the proposed method effectively addresses the issue of low mechanical equipment fault data density, leading to improved accuracy in fault detection and classification, along with a certain level of robustness. [ABSTRACT FROM AUTHOR]

For the next coming years, metaverse, digital twin and autonomous vehicle applications are the leading technologies for many complex applications hitherto inaccessible such as health and life sciences, smart home, smart agriculture, smart city, smart car and logistics, Industry 4.0, entertainment (video game) and social media applications, due to recent tremendous developments in process modeling, supercomputing, cloud data analytics (deep learning, etc.), communication network and AIoT/IIoT/IoT technologies. AIoT/IIoT/IoT is a crucial research field because it provides the essential data to fuel metaverse, digital twin, real-time Industry 4.0 and autonomous vehicle applications. However, the science of AIoT is inherently multidisciplinary, and therefore, it is difficult for readers to understand its evolution and impacts. Our main contribution in this article is to analyze and highlight the trends and challenges of the AIoT technology ecosystem including core hardware (MCU, MEMS/NEMS sensors and wireless access medium), core software (operating system and protocol communication stack) and middleware (deep learning on a microcontroller: TinyML). Two low-powered AI technologies emerge: TinyML and neuromorphic computing, but only one AIoT/IIoT/IoT device implementation using TinyML dedicated to strawberry disease detection as a case study. So far, despite the very rapid progress of AIoT/IIoT/IoT technologies, several challenges remain to be overcome such as safety, security, latency, interoperability and reliability of sensor data, which are essential characteristics to meet the requirements of metaverse, digital twin, autonomous vehicle and Industry 4.0. applications. [ABSTRACT FROM AUTHOR]

Diamond cutting-tool wear has a direct impact on the processing accuracy of the machined surface in ultra-precision diamond cutting. It is difficult to monitor the tool's condition because of the slight wear amount. This paper proposed a hybrid deep learning model for tool wear state prediction in ultra-precision diamond cutting. The cutting force was accurately estimated and the wear state of the diamond tool was predicted by using the hybrid deep learning model with the motion displacement, velocity, and other signals in the machining process. By carrying out machining experiments, this method can classify diamond-tool wear condition with an accuracy of more than 85%. Meanwhile, the effectiveness of the proposed method was verified by comparing it with a variety of machine learning models. [ABSTRACT FROM AUTHOR]

Relevant research has investigated how predictive modeling algorithms, deep-learning-based sensing technologies, and big urban data configure immersive hyperconnected virtual spaces in digital twin cities: digital twin modeling tools, monitoring and sensing technologies, and Internet-of-Things-based decision support systems articulate big-data-driven urban geopolitics. This systematic review aims to inspect the recently published literature on digital twin simulation tools, spatial cognition algorithms, and multi-sensor fusion technology in sustainable urban governance networks. We integrate research developing on how blockchain-based digital twins, smart infrastructure sensors, and real-time Internet of Things data assist urban computing technologies. The research problems are whether: data-driven smart sustainable urbanism requires visual recognition tools, monitoring and sensing technologies, and simulation-based digital twins; deep-learning-based sensing technologies, spatial cognition algorithms, and environment perception mechanisms configure digital twin cities; and digital twin simulation modeling, deep-learning-based sensing technologies, and urban data fusion optimize Internet-of-Things-based smart city environments. Our analyses particularly prove that virtual navigation tools, geospatial mapping technologies, and Internet of Things connected sensors enable smart urban governance. Digital twin simulation, data visualization tools, and ambient sound recognition software configure sustainable urban governance networks. Virtual simulation algorithms, deep learning neural network architectures, and cyber-physical cognitive systems articulate networked smart cities. Throughout January and March 2023, a quantitative literature review was carried out across the ProQuest, Scopus, and Web of Science databases, with search terms comprising "sustainable urban governance networks" + "digital twin simulation tools", "spatial cognition algorithms", and "multi-sensor fusion technology". A Preferred Reporting Items for Systematic Reviews and Meta-analysis (PRISMA) flow diagram was generated using a Shiny App. AXIS (Appraisal tool for Cross-Sectional Studies), Dedoose, MMAT (Mixed Methods Appraisal Tool), and the Systematic Review Data Repository (SRDR) were used to assess the quality of the identified scholarly sources. Dimensions and VOSviewer were employed for bibliometric mapping through spatial and data layout algorithms. The findings gathered from our analyses clarify that Internet-of-Things-based smart city environments integrate 3D virtual simulation technology, intelligent sensing devices, and digital twin modeling. [ABSTRACT FROM AUTHOR]

Weld site inspection is a research area of interest in the manufacturing industry. In this study, a digital twin system for welding robots to examine various weld flaws that might happen during welding using the acoustics of the weld site is presented. Additionally, a wavelet filtering technique is implemented to remove the acoustic signal originating from machine noise. Then, an SeCNN-LSTM model is applied to recognize and categorize weld acoustic signals according to the traits of strong acoustic signal time sequences. The model verification accuracy was found to be 91%. In addition, using numerous indicators, the model was compared with seven other models, namely, CNN-SVM, CNN-LSTM, CNN-GRU, BiLSTM, GRU, CNN-BiLSTM, and LSTM. A deep learning model, and acoustic signal filtering and preprocessing techniques are integrated into the proposed digital twin system. The goal of this work was to propose a systematic on-site weld flaw detection approach encompassing data processing, system modeling, and identification methods. In addition, our proposed method could serve as a resource for pertinent research. [ABSTRACT FROM AUTHOR]

Digital twin technology can be used for disaster safety management of underground utility tunnels, which are social infrastructures. To verify its efficiency in an underground utility tunnel, it must be implemented and monitored in the real world. Therefore, the state of information about an object and the position of an object in the real world, which can change upon movement, should be correspondingly reflected in the digital model. Underground utility tunnels are monitored through closed circuit television (CCTV) cameras because the main infrastructure facilities are installed in a long and narrow form, which limits access to them. Therefore, synchronization of a digital twin model of an underground utility tunnel requires a method for identifying the location of an object through an installed CCTV camera. This study compares the DenseDepth transfer learning method and the coordinate system conversion method through floor plan projection to estimate depth using a single CCTV camera installed in an underground utility tunnel. The coordinate system conversion method through floor plane projection showed an error of 0.23 m to 1.5 m within a 50 m range. The DenseDepth transfer learning method showed an error of 1 m to 3 m; therefore, it was considered unsuitable for distance estimation. The coordinate system conversion method through floor plane projection showed a smaller error even at a longer distance than the DenseDepth transfer learning method. Therefore, the coordinate system conversion method through floor plane projection was considered more suitable than the DenseDepth transfer learning method for depth estimation using a single camera. [ABSTRACT FROM AUTHOR]

Due to the complexity of the oil and gas station system, the operational data, with various temporal dependencies and inter-metric dependencies, has the characteristics of diverse patterns, variable working conditions and imbalance, which brings great challenges to multivariate time series anomaly detection. Moreover, the time-series reconstruction information of data from digital twin space can be used to identify and interpret anomalies. Therefore, this paper proposes a digital twin-driven MTAD-GAN (Multivariate Time Series Data Anomaly Detection with GAN) oil and gas station anomaly detection method. Firstly, the operational framework consisting of digital twin model, virtual-real synchronization algorithm, anomaly detection strategy and realistic station is constructed, and an efficient virtual-real mapping is achieved by embedding a stochastic Petri net (SPN) to describe the station-operating logic of behavior. Secondly, based on the potential correlation and complementarity among time series variables, we present a MTAD-GAN anomaly detection method to reconstruct the error of multivariate time series by combining mechanism of knowledge graph attention and temporal Hawkes attention to judge the abnormal samples by a given threshold. The experimental results show that the digital twin-driven anomaly detection method can achieve accurate identification of anomalous data with complex patterns, and the performance of MTAD-GAN anomaly detection is improved by about 2.6% compared with other methods based on machine learning and deep learning, which proves the effectiveness of the method. [ABSTRACT FROM AUTHOR]

In metaverse, a digital‐twin smart home is a vital platform for immersive communication between the physical and virtual world. Triboelectric nanogenerators (TENGs) sensors contribute substantially to providing smart‐home monitoring. However, TENG deployment is hindered by its unstable output under environment changes. Herein, we develop a digital‐twin smart home using a robust all‐TENG based information mat (InfoMat), which consists of an in‐home mat array and an entry mat. The interdigital electrodes design allows environment‐insensitive ratiometric readout from the mat array to cancel the commonly experienced environmental variations. Arbitrary position sensing is also achieved because of the interval arrangement of the mat pixels. Concurrently, the two‐channel entry mat generates multi‐modality information to aid the 10‐user identification accuracy to increase from 93% to 99% compared to the one‐channel case. Furthermore, a digital‐twin smart home is visualized by real‐time projecting the information in smart home to virtual reality, including access authorization, position, walking trajectory, dynamic activities/sports, and so on. [ABSTRACT FROM AUTHOR]

As a fundamental service in near future, medical digital twin (MDT) is the virtual replica of a person. MDT applies new technologies of IoT, AI and big data to predict the state of health and offer clinical suggestions. It is crucial to secure medical digital twins through deep understanding of the design of digital twins and applying the new vulnerability tolerant approach. In this paper, we present a new medical digital twin, which systematically combines Haptic-AR navigation and deep learning techniques to achieve virtual replica and cyber–human interaction. We report an innovative study of the cyber–human interaction performance in different scenarios. With the focus on cyber resilience, a new solution of vulnerability tolerant is the must in the real-world MDT scenarios. We propose a novel scheme for recognising and fixing MDT vulnerabilities, in which a new CodeBERT-based neural network is applied to better understand risky code and capture cybersecurity semantics. We develop a prototype of the new MDT and collect several real-world datasets. In the empirical study, a number of well-designed experiments are conducted to evaluate the performance of digital twin, cyber–human interaction and vulnerability detection. The results confirm that our new platform works well, can support clinical decision and has great potential in cyber resilience. [ABSTRACT FROM AUTHOR]

Floods have been among the costliest hydrometeorological hazards across the globe for decades, and are expected to become even more frequent and cause larger devastating impacts in cities due to climate change. Digital twin technologies can provide decisionmakers with effective tools to rapidly evaluate city resilience under projected floods. However, the development of city digital twins for flood predictions is challenging due to the time-consuming, uncertain processes of developing, calibrating, and coupling physics-based hydrologic and hydraulic models. In this study, a flood prediction methodology (FPM) that integrates synchronization analysis and deep-learning is developed to directly simulate the complex relationships between rainfall and flood characteristics, bypassing the computationally expensive hydrologic-hydraulic models, with the City of Calgary being used for demonstration. The developed FPM presents the core of data-driven digital twins that, with real-time sensor data, can rapidly provide early warnings before flood realization, as well as information about vulnerable areas—enabling city resilience planning considering different climate change scenarios. [ABSTRACT FROM AUTHOR]

The occurrence of forest fires can impact vegetation in the ecosystem, property, and human health, but also indirectly affect the climate. JULES-INFERNO is a global land surface model, which simulates vegetation, soils, and fire occurrence driven by environmental factors. However, this model incurs substantial computational costs due to the high data dimensionality and the complexity of differential equations. Deep learning-based digital twins have an advantage in handling large amounts of data. They can reduce the computational cost of subsequent predictive models by extracting data features through Reduced Order Modelling (ROM) and then compressing the data to a low-dimensional latent space. This study proposes a JULES-INFERNO-based digital twin fire model using ROM techniques and deep learning prediction networks to improve the efficiency of global wildfire predictions. The iterative prediction implemented in the proposed model can use current-year data to predict fires in subsequent years. To avoid the accumulation of errors from the iterative prediction, Latent data Assimilation (LA) is applied to the prediction process. LA manages to efficiently adjust the prediction results to ensure the stability and sustainability of the prediction. Numerical results show that the proposed model can effectively encode the original data and achieve accurate surrogate predictions. Furthermore, the application of LA can also effectively adjust the bias of the prediction results. The proposed digital twin also runs 500 times faster for online predictions than the original JULES-INFERNO model without requiring High-Performance Computing (HPC) clusters. The implementation code of this study and the developed models are available at https://github.com/DL-WG/Digital-twin-LA-global-wildfire. [ABSTRACT FROM AUTHOR]

• This study utilizes the integration of finite element simulation data and actual detection data to establish digital twin detection information. • An adaptively updating defect detection model based on GANS-ResNet50-RA is proposed. • The method effectively enhances detection accuracy and generalizes well across various settings, even with limited sample sizes. To enhance the efficiency and intelligence of laser ultrasonic detection of metal surface defects, a detection method based on digital twins is proposed. Given the scarcity of defect samples and the difficulty of obtaining labeled data in practical applications, the finite element method is used to construct a laser ultrasonic metal defect detection model, effectively generating twin data for defect detection. With the help of generative adversarial networks, the distribution difference between twin data and real data is minimized. Additionally, by using continuous wavelet transform, one-dimensional ultrasonic signals are converted into two-dimensional time–frequency images for detection input. In terms of detection algorithm development, a residual network with an optimized global attention mechanism is introduced to ensure real-time synchronization and updates between the digital twin model and the actual laser ultrasonic detection equipment. Finally, experimental validation of the proposed method shows that it effectively addresses the issue of small sample sizes in defect detection and achieves high detection accuracy. Moreover, comparative experiments on crack defect migration tasks under different settings demonstrate the method's good generalization ability. [ABSTRACT FROM AUTHOR]